Search NASA⌕ Search

SEARCH · Search NASA

Results for “adaptation models”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Deep-learning-based domain adaptation for cavity fault prediction at Jefferson Laboratory

Superconducting radio-frequency (SRF) cavities are the core components of the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab, providing high-power electron beams for nuclear physics experiments. The facility comprises 418 SRF cavities, and any fault in these cavities can lead to interruptions in the electron beam supply. Cavity faults are the leading cause of beam trips in CEBAF. Predicting and mitigating those faults before onset can help maintain normal operation. Existing models face challenges in distinguishing between normal and fault signals when changes occur in the underlying time-series data, from changes in control software, operational parameters, or the environment. This work proposes a deep learning domain adaptation model that leverages transfer learning to address fault prediction challenges by improving accuracy. The model is trained and fine-tuned using a dataset collected for faulty and normal operation using a data acquisition system in CEBAF. Our deep learning-based domain adaptation model achieves a prediction accuracy of 89.61% of the fault and normal signals. The developed model effectively predicts normal running signals compared to the baseline approach without domain adaptation. This capacity is essential for the fault prediction task in the CEBAF because of heavily imbalanced data containing vast amounts of normal signals. The model performs well for predicting faults several hundred milliseconds before the fault onset compared to other models where no adaptation is applied. Incorporating deep learning-based domain adaptation techniques will significantly improve the fault prediction performance.

Rahman, Md Monibor [Old Dominion Univ., Norfolk, V↗
DOE OSTI2024

Diverse fates of ancient horizontal gene transfers in extremophilic red algae

Abstract Horizontal genetic transfer (HGT) is a common phenomenon in eukaryotic genomes. However, the mechanisms by which HGT‐derived genes persist and integrate into other pathways remain unclear. This topic is of significant interest because, over time, the stressors that initially favoured the fixation of HGT may diminish or disappear. Despite this, the foreign genes may continue to exist if they become part of a broader stress response or other pathways. The conventional model suggests that the acquisition of HGT equates to adaptation. However, this model may evolve into more complex interactions between gene products, a concept we refer to as the ‘Integrated HGT Model’ (IHM). To explore this concept further, we studied specialized HGT‐derived genes that encode heavy metal detoxification functions. The recruitment of these genes into other pathways could provide clear examples of IHM. In our study, we exposed two anciently diverged species of polyextremophilic red algae from the Galdieria genus to arsenic and mercury stress in laboratory cultures. We then analysed the transcriptome data using differential and coexpression analysis. Our findings revealed that mercury detoxification follows a ‘one gene‐one function’ model, resulting in an indivisible response. In contrast, the ars H gene in the arsenite response pathway demonstrated a complex pattern of duplication, divergence and potential neofunctionalization, consistent with the IHM. Our research sheds light on the fate and integration of ancient HGTs, providing a novel perspective on the ecology of extremophiles.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Point cloud-based diffusion models for the Electron-Ion Collider

At high-energy collider experiments, generative models can be used for a wide range of tasks, including fast detector simulations, unfolding, searches of physics beyond the Standard Model, and inference tasks. In particular, it has been demonstrated that score-based diffusion models can generate high-fidelity and accurate samples of jets or collider events. This work expands on previous generative models in three distinct ways. First, our model is trained to generate entire collider events, including all particle species with complete kinematic information. We quantify how well the model learns event-wide constraints such as the conservation of momentum and discrete quantum numbers. We focus on the events at the future Electron-Ion Collider, but we expect that our results can be extended to proton-proton and heavy-ion collisions. Second, previous generative models often relied on image-based techniques. The sparsity of the data can negatively affect the fidelity and sampling time of the model. We address these issues using point clouds and a novel architecture combining edge creation with transformer modules called Point Edge Transformers. Third, we adapt the foundation model OmniLearn, to generate full collider events. This approach may indicate a transition toward adapting and fine-tuning foundation models for downstream tasks instead of training new models from scratch.

Araz, Jack Y. [Stony Brook Univ., NY (United State↗
DOE OSTI2025

Representing lateral groundwater flow from land to river in Earth system models

Lateral groundwater flow (LGF) is an important hydrologic process in controlling water table dynamics. Due to the relatively coarse spatial resolutions of land surface models, the representation of this process is often overlooked or overly simplified. In this study, we developed a hillslope-based lateral groundwater flow model. Specifically, we first developed a hillslope definition model based on an existing watershed delineation model to represent the subgrid spatial variability in topography. Building upon this hillslope definition, we then developed a physical-based lateral groundwater flow using Darcy’s equation. This model explicitly considers the relationships between the groundwater table along the hillslope and the river water table levels. We coupled this intra-grid model to the land component (E3SM Land Model: ELM) and river component (MOdel for Scale Adaptive River Transport: MOSART) of the Energy Exascale Earth System Model (E3SM). We tested both the hillslope definition model and the lateral groundwater flow model and performed sensitivity experiments using different configurations. Simulations for a single grid cell at 0.5°×0.5° within the Amazon basin show that the definition of hillslope is the key to modeling lateral flow processes and the runoff partition between surface and subsurface can be dramatically changed using the hillslope approach. Although our method provides a pathway to improve the lateral flow process, future improvements are needed to better capture the subgrid structure to account for the spatial variability in hillslopes within the simulated grid of land surface models.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Generalized Bayesian MARS: Tools for Stochastic Computer Model Emulation

The multivariate adaptive regression spline (MARS) approach of Friedman and its Bayesian counterpart are effective approaches for the emulation of computer models. The traditional assumption of Gaussian errors limits the usefulness of MARS, and many popular alternatives, when dealing with stochastic computer models. Here, we propose a generalized Bayesian MARS (GBMARS) framework which admits the broad class of generalized hyperbolic distributions as the induced likelihood function. This allows us to develop tools for the emulation of stochastic simulators which are parsimonious, scalable, and interpretable and require minimal tuning, while providing powerful predictive and uncertainty quantification capabilities. GBMARS is capable of robust regression with t distributions, quantile regression with asymmetric Laplace distributions, and a general form of “Normal-Wald” regression in which the shape of the error distribution and the structure of the mean function are learned simultaneously. We demonstrate the effectiveness of GBMARS on various stochastic computer models, and we show that it compares favorably to several popular alternatives.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Dynamic Control of Sodium Cold Trap Purification Temperature Using LSTM System Identification

This study investigates the dynamic regulation of the sodium cold trap purification temperature at Argonne National Laboratory’s liquid sodium test facility, employing long short-term memory (LSTM) system identification techniques. The investigation introduces an innovative hybrid approach by integrating model predictive control (MPC) based on first principles dynamic models with a multi-step time–frequency LSTM model in predicting the temperature profiles of a sodium cold trap purification system. The long short-term memory–model predictive controller (LSTM-MPC) model employs a sliding window scheme to gather training samples for multi-step prediction, leveraging historical data to construct predictive models that capture the non-linearities of the complex system dynamics without explicitly modeling the underlying physical processes. The performance of the LSTM-MPC and MPC were evaluated through simulation experiments, where both models were assessed on their capacity to maintain the cold trap temperature within predefined set-points while minimizing deviations and overshoots. Results obtained show how the data-driven LSTM-MPC model demonstrates stability and adaptability. In contrast, the traditional MPC model exhibits irregularities, particularly evident as overshoots around set-point limits, which can potentially compromise its effectiveness over long prediction time intervals. The findings obtained offer valuable insights into integrating data-driven techniques for enhancing real-time monitoring systems.

LSTM-MPC↗
DOE OSTI2025

A novel transformation of the ice sheet Stokes equations and some of its properties and applications

We introduce a novel transformation of the Stokes equations into a form closely resembling the shallow Blatter–Pattyn equations. The two forms differ by only a few additional terms, while their variational formulations differ only by a single term in each horizontal direction. Specifically, the variational formulation of the Blatter–Pattyn model drops the vertical velocity in the second invariant of the strain rate tensor. Here we make use of the new transformation in two ways. First, we consider incorporating the transformed equations into a code that can be very easily converted from a Stokes to a Blatter–Pattyn model, and vice versa, by switching these terms on or off. This may be generalized so that the Stokes model is switched on adaptively only where the Blatter–Pattyn model loses accuracy. Second, the key role played by the vertical velocity in the Blatter–Pattyn approximation motivates new approximations. Two examples are presented. These require a mesh that enables the discrete continuity equation to be invertible for the vertical velocity in terms of the horizontal velocity components. Examples of such meshes, such as the first-order P1–E0 mesh and the second-order P2–E1 mesh, are given in both 2D and 3D. However, the transformed Stokes model has the same type of gravity forcing as the Blatter–Pattyn model, determined by the ice surface slope, thereby forgoing some of the mesh generality of the traditional formulation of the Stokes model.

58 GEOSCIENCES↗
DOE OSTI2025

Balancing Trade-offs: Adaptive Differential Privacy in Interpretable Machine Learning Models

In the advancing field of machine learning, balancing accuracy, interpretability, and privacy represents a significant challenge. The problem is exacerbated by the widespread deployment of pre-trained models locally in diverse applications, which could lead to various amounts of privacy leakage. Conventional Differential Privacy strategies, in which uniform noises are applied to model gradients, guarantee data privacy at the expense of accuracy and interpretability. This paper introduces a Feature-Sensitive Adaptive Differential Privacy (FADP) framework with a unique noise-adding strategy. Noises are adaptively added based on feature importance clustering, where important features are considered for interpretability. By employing a unique masking technique, FADP selectively preserves crucial features with minimal noise interference, maintaining accuracy while enhancing interpretability. The FADP framework addresses the limitations of traditional DP methods by preserving critical channels and improving interpretability — a vital requirement in machine learning applications that demand transparency in model decisions. Through comprehensive testing, FADP is shown to balance the trade-offs among accuracy, privacy, and interpretability, marking a substantial advancement in the field of privacy-preserving machine learning.

Farhad Riya, Farhin [University of Tennessee, Knox↗
DOE OSTI2025

Surrogate-constructed scalable-circuits adaptive variational quantum eigensolver in the Schwinger model

Inspired by recent advancements in simulating periodic systems on quantum computers, we develop an approach to further advance the simulation of these systems, named (SC) 2 -ADAPT-VQE. Our approach extends the scalable-circuits ADAPT-VQE framework, which builds an ansatz from a pool of coordinate-invariant operators defined for arbitrarily large, though not arbitrarily small, volumes. Our method uses a classically tractable “surrogate constructed” method to remove irrelevant operators from the pool, reducing the minimum size for which the scalable circuits are defined. Bringing together the scalable circuits and the surrogate constructed approaches forms the core of the (SC) 2 methodology. Our approach allows for a wider set of classical computations on small volumes, which can be used for a more robust extrapolation protocol. While developed in the context of lattice models, the surrogate construction portion is applicable to a wide variety of problems where information about the relative importance of operators in the pool is available. As an example, we use it to compute the properties of the Schwinger model—quantum electrodynamics for a single, massive fermion in 1 +1 dimensions—and show that our method can be used to accurately extrapolate to the continuum limit.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2025

OmniXAS: A universal deep-learning framework for materials x-ray absorption spectra

X-ray absorption spectroscopy (XAS) is a powerful characterization technique for probing the local chemical environment of absorbing atoms. However, analyzing XAS data presents significant challenges, often requiring extensive, computationally intensive simulations, as well as significant domain expertise. These limitations hinder the development of fast, robust XAS analysis pipelines that are essential in high-throughput studies and for autonomous experimentation. Here, we address these challenges with OmniXAS, a framework that contains a suite of transfer learning approaches for XAS prediction, each uniquely contributing to improved accuracy and efficiency, as demonstrated on the K-edge spectra database covering eight 3⁢d transition metals (Ti–Cu). The OmniXAS framework is built upon three distinct strategies. First, we use M3GNet [Nat. Comput. Sci. 2, 718 (2022)] to derive latent representations of the local chemical environment of absorption sites as input for XAS prediction, achieving significant improvements over conventional featurization techniques. Second, we employ a hierarchical transfer learning strategy, training a universal multitask model across elements before fine-tuning for element-specific predictions. Models based on this cascaded approach after elementwise fine-tuning outperform element-specific models by up to 69%. Third, we implement cross-fidelity transfer learning, adapting a universal model to predict spectra generated by simulation of a different fidelity with a much higher computational cost. This approach improves prediction accuracy by up to 11% over models trained on the target fidelity alone. Our approach significantly boosts the throughput of XAS modeling by orders of magnitude as compared to first-principles simulations and is extendable to XAS prediction for a broader range of elements. The proposed transfer learning framework is generalizable to enhance deep-learning models that target other properties in materials research.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Generative Models for Crystalline Materials

Understanding structure-property relationships in materials is fundamental in condensed matter physics and materials science. Over the past few years, machine learning (ML) has emerged as a powerful tool for advancing this understanding and accelerating materials discovery. Early ML approaches primarily focused on constructing and screening large material spaces to identify promising candidates for various applications. More recently, research efforts have increasingly shifted toward generating crystal structures using end-to-end generative models. This review analyzes the current state of generative modeling for crystal structure prediction and de novo generation. It examines crystal representations, outlines the generative models used to design crystal structures, and evaluates their respective strengths and limitations. Furthermore, the review highlights experimental considerations for evaluating generated structures and provides recommendations for suitable existing software tools. Emerging topics, such as modeling disorder and defects, integration in advanced characterization, incorporating synthetic feasibility constraints, and model explainability are explored. Ultimately, this work aims to inform both experimental scientists looking to adapt suitable ML models to their specific circumstances and ML specialists seeking to understand the unique challenges related to inverse materials design and discovery.

Metni, Houssam [Karlsruhe Inst. of Technology (KIT↗
DOE OSTI2024

Reinforcement Learning as a Parsimonious Alternative to Prediction Cascades: A Case Study on Image Segmentation

Deep learning architectures have achieved state-of-the-art (SOTA) performance on computer vision tasks such as object detection and image segmentation. This may be attributed to the use of over-parameterized, monolithic deep learning architectures executed on large datasets. Although such large architectures lead to increased accuracy, this is usually accompanied by a larger increase in computation and memory requirements during inference. While this is a non-issue in traditional machine learning (ML) pipelines, the recent confluence of machine learning and fields like the Internet of Things (IoT) has rendered such large architectures infeasible for execution in low-resource settings. For some datasets, large monolithic pipelines may be overkill for simpler inputs. To address this problem, previous efforts have proposed decision cascades where inputs are passed through models of increasing complexity until the desired performance is achieved. However, we argue that cascaded prediction leads to sub-optimal throughput and increased computational cost due to wasteful intermediate computations. To address this, we propose PaSeR (Parsimonious Segmentation with Reinforcement Learning) a non-cascading, cost-aware learning pipeline as an efficient alternative to cascaded decision architectures. Through experimental evaluation on both real-world and standard datasets, we demonstrate that PaSeR achieves better accuracy while minimizing computational cost relative to cascaded models. Further, we introduce a new metric IoU/GigaFlop to evaluate the balance between cost and performance. On the real-world task of battery material phase segmentation, PaSeR yields 179% improvement over SOTA MatPhase model and a 196% improvement over IDK Cascades under the IoU/GigaFlop metric. We also demonstrate PaSeR’s adaptability to complementary models trained on a noisy MNIST dataset, where it outperforms all baselines on IoU/GigaFlop by an average of 44%.

Srikshan, Bharat↗
DOE OSTI2024

Controlling cantilevered adaptive X-ray mirrors

Modeling the behavior of a prototype cantilevered X-ray adaptive mirror (held from one end) demonstrates its potential for use on high-performance X-ray beamlines. Similar adaptive mirrors are used on X-ray beamlines to compensate optical aberrations, control wavefronts and tune mirror focal distances at will. Controlled by 1D arrays of piezoceramic actuators, these glancing-incidence mirrors can provide nanometre-scale surface shape adjustment capabilities. However, significant engineering challenges remain for mounting them with low distortion and low environmental sensitivity. Finite-element analysis is used to predict the micron-scale full actuation surface shape from each channel and then linear modeling is applied to investigate the mirrors' ability to reach target profiles. Using either uniform or arbitrary spatial weighting, actuator voltages are optimized using a Moore–Penrose matrix inverse, or pseudoinverse, revealing a spatial dependence on the shape fitting with increasing fidelity farther from the mount.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

CMIP7 data request: impacts and adaptation priorities and opportunities

The Coupled Model Intercomparison Project Phase 7 (CMIP7) undertook an extensive process to gather community input and refine data requests related to impacts and adaptation applications of Earth System Model (ESM) outputs. The Impacts and Adaptation (I&A) Data Request Team worked with CMIP7 leadership to distribute an open solicitation across many communities that use climate model outputs requesting inputs for new and existing variables, the most applicable temporal characteristics, and groupings of variables that together allow for specific application opportunities. This input was then collated and translated into CMIP7 standard templates for inclusion in the broader data request, leading to 13 I&A data request opportunities, 60 variable groups and 539 unique variables sought by vulnerability, impacts, adaptation, and climate services user communities. Here, we describe these opportunities and variable groups, as well as new insights into how ESM groups can prioritize outputs that set off a chain of further analyses, ultimately informing decisions impacting society and natural systems. These include an emphasis on high-resolution outputs to allow further modeling of climate impacts at regional and local scales, improved representation of extreme weather events, enhanced accuracy of downscaling and bias-adjustment techniques, and support for more detailed assessments for decision-making in adaptation and mitigation strategies. There is also broad interest in more extensive provisioning of two-dimensional variables at the Earth's surface, prioritizing experiments that enhance our understanding of both the recent past and future scenarios, and providing outputs that allow further downscaling and bias adjustment. We emphasize that variable groups are the fundamental level at which to engage with the I&A data request, matching the scale of input and the way output provision enables specific I&A applications. Given resource constraints, we applaud CMIP7 efforts to foster strong engagement and communication between ESM groups and the I&A team to build consensus around prudent compromises in priority variables, temporal resolutions, simulation experiments, time subsets, and ensemble members.

Ruane, Alex C. [NASA Goddard Inst. for Space Studi↗
DOE OSTI2024

Adaptive gene loss in the common bean pan-genome during range expansion and domestication

The common bean ( Phaseolus vulgaris L.) is a crucial legume crop and an ideal evolutionary model to study adaptive diversity in wild and domesticated populations. Here, we present a common bean pan-genome based on five high-quality genomes and whole-genome reads representing 339 genotypes. It reveals ~234 Mb of additional sequences containing 6,905 protein-coding genes missing from the reference, constituting 49% of all presence/absence variants (PAVs). More non-synonymous mutations are found in PAVs than core genes, probably reflecting the lower effective population size of PAVs and fitness advantages due to the purging effect of gene loss. Our results suggest pan-genome shrinkage occurred during wild range expansion. Selection signatures provide evidence that partial or complete gene loss was a key adaptive genetic change in common bean populations with major implications for plant adaptation. The pan-genome is a valuable resource for food legume research and breeding for climate change mitigation and sustainable agriculture.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

In vivo evaluation of an adaptive resuscitation controller using whole blood and crystalloid infusates for hemorrhagic shock

Introduction Hemorrhage remains the leading cause of preventable death on the battlefield. The most effective means to increase survivability is early hemorrhage control and fluid resuscitation. Unfortunately, fluid resuscitation requires constant adjustments to ensure casualty is properly managed, which is often not feasible in the pre-hospital setting. In this study, we showed how an adaptive closed-loop controller for hemorrhage resuscitation can be used to automate hemodynamic management using a swine hemorrhagic shock injury model. Methods The adaptive resuscitation controller (ARC) was previously developed to track pressure–volume responsiveness in real time and adjust its infusion rate to reach the target mean arterial pressure (MAP). Swine while maintained under a surgical plane of anesthesia and analgesia underwent a splenectomy, followed by two hemorrhage and resuscitation events. For the first resuscitation event, hemorrhage was induced to reduce the MAP to 35 mmHg until arterial lactate reached 4 mmol/L. The ARC system then infused whole blood (WB) to reach the target MAP and maintained the subject using crystalloids for 120 min. For the second resuscitation event, the subjects were hemorrhaged again but resuscitated using only crystalloid infusion to reach the target MAP and 120-min maintenance. Results The ARC was effective at WB resuscitation, reaching the target MAP in 2.0 ± 1.0 min. The median performance error was 1.1% ± 4.6%, and target overshoot was 14.4% ± 7.0% of the target MAP. The ARC maintained all animals throughout the 120 min maintenance period. For the second crystalloid-based resuscitation, ARC required a longer time to reach the target MAP, at an average rise time of 4.3 ± 4.0 min. However, target overshoot was reduced to 8.4% ± 7.3% of the target MAP. Much higher flow rates were required to maintain the target MAP during the second resuscitation event than during the first resuscitation event. Discussion The ARC was able to rapidly reach and maintain the target MAP effectively. However, this sometimes required large volumes of fluid as the ARC’s only goal was to reach the target MAP. Further clinical insight is needed regarding the preferred aggression level to achieve the target MAP. In conclusion, the ARC was successful in its programmed objective of reaching and maintaining the target MAP for extended periods of time in vivo , a critical next step toward improving hemorrhage treatment in the pre-hospital environment.

Snider, Eric J.↗
DOE OSTI2026

ELM‐MOSART‐DOC: A Large‐Scale Riverine Dissolved Organic Carbon Model and Its Application Over the United States

Riverine dissolved organic carbon (DOC), primarily sourced from soil organic carbon (SOC), plays a crucial role in regional and global carbon cycles. However, the complexities of the underlying mechanisms and limited observations present significant challenges for predictive understanding of DOC at regional or larger scales. Recently, we developed a machine learning‐based (ML) map of DOC transformation rates, bridging the gap between SOC and DOC leaching flux and simplifying terrestrial DOC representation. Building on this advancement, we introduce ELM‐MOSART‐DOC, a DOC module integrated into the riverine component of the Energy Exascale Earth System Model (E3SM)—the Model for Scale Adaptive River Transport (MOSART). ELM‐MOSART‐DOC simulates DOC transport and transformation across both headwater streams and river networks, including those managed. Model validation demonstrates the ability of ELM‐MOSART‐DOC to accurately capture long‐term average DOC concentrations, with Kling‐Gupta Efficiency (KGE) scores of 0.58 and 0.76 at large and local stations, respectively. We further assess the impact of reservoirs through different simulation schemes, revealing that reservoirs significantly alter DOC fluxes by regulating streamflow patterns and promoting DOC mineralization. Model simulations indicate that reservoirs reduce total DOC flux from the Mississippi River into the ocean by 7.5%, with the long‐term average annual export decreasing from 3.34 to 3.14 teragrams (Tg) per year. ELM‐MOSART‐DOC integrates process‐based modeling with ML parameterization to enhance the predictive understanding of riverine biogeochemical processes. This approach reduces uncertainties in modeling regional and global carbon cycle ESMs and provides new insights into carbon cycling and its implications for global environmental change.

Li, Lingbo [Univ. of Houston, TX (United States); ↗